Fast LLM & Agents & MCPs

- Covers LLM architectures, RAG, fine‑tuning, and prompt engineering.
- Provides sample agents with LangChain & LangGraph (v1.0.0).
- Provides sample agents with AWS Strands Agents.
- Provides sample agents with Google Agent Development Kit (ADK).
- Includes MCP Tool integration samples (local and remote).
- Explains concepts of agents, tools, skills, and A2A protocol.

Clone the repository and navigate to the relevant sample directories under agents/ for each framework. No specific server configuration or invocation command is documented; users should follow the individual sample READMEs or setup instructions inside each directory.

def get_capital_city(country: str) -> str:
"""Retrieves the capital city for a given country."""

capital_agent = LlmAgent(
model="gemini-3.0-pro",
name="capital_agent",
description="Answers user questions about the capital city of a given country.",
instruction="""You are an agent that provides the capital city of a country... (previous instruction text)""",
tools=[get_capital_city]
)
```

A Tool represents a specific capability provided to an AI agent, enabling it to perform actions and interact with the world beyond its core text generation and reasoning abilities.

- Function Tool: Transforming a function into a tool is a straightforward way to integrate custom logic into your agents.
- Agent-as-Tool: This powerful feature allows you to leverage the capabilities of other agents within your system by calling them as tools. The Agent-as-a-Tool enables you to invoke another agent to perform a specific task, effectively delegating responsibility.
- Google ADK Built-in-Tools: These built-in tools provide ready-to-use functionality such as Google Search or code executors that provide agents with common capabilities.
- Langchain Tools: Also used in Google ADK as Langchain Tools.
- https://python.langchain.com/docs/integrations/tools/
- CrewAI Tools: Also used in Google ADK as CrewAI Tools.
- https://docs.crewai.com/concepts/tools
- MCP Tools: Connects MCP server apps to MCP Clients (Claude App, VSCode, etc,) or Agents (Google ADK).
- MCP Servers: https://github.com/modelcontextprotocol/servers